Research Associate/Senior Research Associate in Data Fusion for TORUS Programme
The successful applicant will be based at the University of Bristol to work on the EPSRC TORUS Programme.
Acure for Parkinson's disease has been held back for decades by the extreme difficulty of measuring whether proposed new drugs actually improvethe patient's symptoms and daily life. TORUSaims to solve this through a novel platform of sensing technologies for use in patients' own homes along with an advanced data fusion and machine learning pipeline that measures changes in specific mobility-related behavioursover time. Thus, TORUS will create the capability to autonomously, continuously and objectively measure mobility-related symptoms of illness during the clinical trial of a new drug, in the patient's own home and for months at a time.TORUS will achieve this goal by using wrist-worn wearables integrated with AI-enabled cameras, led by codesign to ensurethat decisions reflect the views and priorities of diverse patients & families.
What will you be doing?
The successful applicant will:
* Perform fundamental and applied research, within the TORUS data fusion and distributed machine learning team, in the key project area of human-behaviour analysis using spatiotemporal data from different sources and modalities.
* Contribute to the design of the TORUS computational architecture, including the planning of data collection activities with patients.
* Implement these procedures and techniques in the TORUS system.
* Publish the work in top journals and international conferences.
* Present the work in seminars and workshops as appropriate.
* Attend regular project meetings.
* Prepare progress reports for the TORUS management team and advisory board.
* Advise on and participate in deployment activities related to the TORUS system.
You should apply if
* PhD in machine learning (or working towards one for Grade I), data science, artificial intelligence or related research area.
* Excellent and broad conceptual and practical knowledge of the state of the art in machine learning and data science.
* Demonstrably excellent software development skills with Python and relevant libraries (scikit-learn, PyTorch/TensorFlow, and others).
* Proven deep understanding of and demonstrable skills in data-driven experiments and performance evaluation.
* First-authored publications on relevant topics in top-tier international conferences and workshops.
* Excellent communication and presentation skills.
* Proven ability to work both independently and as part of a team (TORUS is a very large project and team working will be a daily activity).
* Proven ability to plan, manage and prioritise own workload while responding to the changing priorities and needs of a busy, dynamic environment.
* Track record in time series analysis or activity recognition for healthcare.
* Interest in health applications of data science.
To find out more about what it's like to work in the Faculty of Engineering, and how the Faculty supports people to achieve their potential, please see our staff blog:
Contract type: Open ended with fixed funding for 18 months
Work pattern: Full time
Grade: I / J
The grade of the role offered will be determined based on the skills, qualifications, and experience you bring to the position.
School/Unit: School of Engineering Mathematics and Technology
This advert will close at 23:59 UK time on Thursday 20th November.
Interview dates will be confirmed in due course.
Our strategy and mission
We recently launched our strategy to 2030 tying together our mission, vision and values.
The University of Bristol aims to be a place where everyone feels able to be themselves and do their best in an inclusive working environment where all colleagues can thrive and reach their full potential. We want to attract, develop, and retain individuals with different experiences, backgrounds and perspectives – particularly people of colour, LGBT+ and disabled people - because diversity of people and ideas remains integral to our excellence as a global civic institution.
#J-18808-Ljbffr